Golden Anchor for Video Generation

Jinyuan Xu; Shitong Shao; Lichen Bai; Zikai Zhou; Guoxi Huang; Nantheera Anantrasirichai; Zeke Xie

cs.CVOct 9, 2026

Golden Anchor for Video Generation

Authors: Jinyuan Xu, Shitong Shao, Lichen Bai, Zikai Zhou, Guoxi Huang, Nantheera Anantrasirichai, Zeke Xie

Organizations: The Hong Kong University of Science and Technology (Guangzhou) · University of Bristol

Abstract

Video generation supports digital content creation, with applications in virtual avatars, AI-driven filmmaking, interactive game engines, and world models. State-of-the-art systems achieve controllability primarily through image-to-video (I2V) generation, in which an injected anchor image determines the identity, composition, and style of the resulting video. In modern pipelines, this anchor is synthesized by a text-to-image (T2I) generator. This raises a largely overlooked question: Are images obtained directly from the T2I model truly suitable for current video models? Our analysis shows that anchor aesthetic and quality scores are weakly correlated with downstream video quality. The structure-and-texture score is negatively correlated with I2V video quality in both the visual and motion dimensions. Fine-tuning the T2I model on an image reward accordingly yields anchors with visibly denser structural and character detail: they score higher on image metrics, yet lower the video reward on every I2V model we test and change downstream motion unpredictably. We therefore introduce Golden Anchor Learning (GAL), to our knowledge the first framework for learning golden anchors by optimizing a T2I generator with downstream video feedback. GAL evaluates candidate anchors through the videos they induce under a frozen I2V model and converts video rewards into image-level preferences for DPO fine-tuning of the T2I generator. On all four I2V models, GAL raises the VBench average by $2.97\%$ -- $8.46\%$ over the untuned generator. The rendered clips also score higher under VideoReward-Overall, and their extracted frames under HPSv3 and UniPercept. GAL yields consistent motion gains across all four I2V models, as measured by a $5.62\%$ -- $38.24\%$ increase in VBench dynamic degree. Although GAL is trained only on HunyuanVideo-1.5 renders, these gains extend to the other three I2V models.

Figures & tables

Figure 1: In the shown examples, the GAL anchor induces more in-scene motion in every one-second interval across all four I2V models. Top: within each I2V-model block, rows are clips rendered from Base (the anchor produced by the untuned image model), GAL-Image (trained based on image rewards), and our GAL anchor (trained based video rewards), under the same prompt and renderer; four frames span each clip. Bottom: line plots of per-interval motion for the same clips, measured as the mean residual optical-flow magnitude inside each one-second interval ( Appendix G ).

Figure 2: Mismatch between image scores and video rewards. Pearson correlation between UniPercept scores of the anchor (IAA: aesthetics; IQA: quality; ISTA: structure and texture) and VideoReward scores of its HunyuanVideo-1.5 render (VQ: visual quality; MQ: motion quality; TA: text alignment) over $49{,}416$ (prompt–anchor–video) records. Aesthetics and quality are nearly uncorrelated with every video axis, and structure/texture is anti-correlated with visual and motion quality.

Figure 3: Overview of GAL. Training (top): For each prompt, we sample $K=4$ anchor images from the T2I generator, render each into a video with a frozen I2V model, and score the videos with a frozen video-reward model. We use these scores to construct image-level preference pairs and fine-tune only the upstream T2I generator with cross-modal DPO. Video rendering, scoring, and pair construction are performed offline. Inference (bottom): The fine-tuned T2I generator produces anchor images that improve video quality, while the downstream I2V model remains unchanged.

	Require: Prompt set $\mathcal{P}$ ; pretrained T2I policy $\pi_{\psi_{0}}$ ; frozen reference $\pi_{\mathrm{ref}}$ ; frozen I2V renderer $G$ ; frozen video reward $R_{v}$ ; T2I noising-context distribution $q_{c}$ ; sibling count $K$ ; margin $m$ ; DPO scale $\beta$ ; step size $\eta$
	Phase 1: Offline preference construction
1:	$\mathcal{D}_{\mathrm{pref}}\leftarrow\varnothing$
2:	for $p\in\mathcal{P}$ do
3:		Sample $K$ sibling anchor images $x_{1},\ldots,x_{K}\sim\pi_{\psi_{0}}(\cdot\mid p)$
		via Eq. 10 with independent Brownian paths
4:		for $k=1,\ldots,K$ do

Algorithm 1 GAL: Golden Anchor Learning

HunyuanVideo-1.5
Variant	Dynamic Degree	Imaging Quality	Aesthetic Quality	Subject Consistency	Motion Smoothness	Overall Consistency	VBench Average
Base	0.8241	0.6586	0.6160	0.9577	0.9922	0.2247	0.7122
GAL (ours)	0.8704	0.7111	0.6426	0.9601	0.9909	0.2248	0.7333
	$(+5.62\%)$	$(+7.97\%)$	$(+4.32\%)$	$(+0.25\%)$	$(-0.13\%)$	$(+0.07\%)$	$(+2.97\%)$
LTX-Video (transfer)
Base	0.5509	0.6493	0.5909	0.9557	0.9922	0.2537	0.6654

Table 1: Main VBench comparison across four I2V models. GAL (ours), the GAL-VideoReward variant, improves the VBench average, dynamic degree, imaging quality, and aesthetic quality over Base on every model. Parentheses give percentage changes from Base; bold marks the best within each model. Open-source results average three I2V seeds; Kling v3 Pro uses one seed.

I2V model	Variant	VideoReward Overall	HPSv3 (video frames)	UniPercept (video frames)
HunyuanVideo-1.5	Base	$-0.014$	7.0025	51.4375
	GAL (ours)	$\bm{+0.131}$	7.6286	55.5926
		$(+0.145)$	$(+0.6261)$	$(+4.1550)$
LTX-Video (transfer)	Base	$-0.328$	6.4788	50.0465
	GAL (ours)	$\bm{-0.224}$	7.3407	54.1946
		$(+0.103)$	$(+0.8619)$	$(+4.1481)$

Table 2: Main reward-model comparison across four I2V models. GAL (ours) improves all three reward scores over Base on every model. VideoReward-Overall scores rendered clips; HPSv3 and UniPercept score their extracted frames. Parentheses give absolute changes from Base.

HunyuanVideo-1.5
Variant	Dynamic Degree	Imaging Quality	Aesthetic Quality	Subject Consistency	Motion Smoothness	Overall Consistency	VBench Average
Base	0.8241	0.6586	0.6160	0.9577	0.9922	0.2247	0.7122
GAL-Image	0.7917	0.7302	0.6453	0.9568	0.9902	0.2230	0.7229
	$(-3.93\%)$	$(+10.87\%)$	$(+4.76\%)$	$(-0.09\%)$	$(-0.20\%)$	$(-0.76\%)$	$(+1.50\%)$
GAL-HPSv3	0.8796	0.7035	0.6310	0.9529	0.9882	0.2248	0.7300
	$(+6.74\%)$	$(+6.82\%)$	$(+2.43\%)$	$(-0.50\%)$	$(-0.41\%)$	$(+0.03\%)$	$(+2.50\%)$

Table 3: Reward-signal ablation within GAL, evaluated with VBench across four I2V models. Parentheses give percentage changes from Base; bold marks the best within each model. GAL-VideoReward is the default variant.

Variant	VideoReward Overall	HPSv3 (video frames)	UniPercept (video frames)
Base	$-0.014$	7.0025	51.4375
GAL-Image	$-0.531$	7.9723	57.2618
	$(-0.517)$	$(+0.9698)$	$(+5.8243)$
GAL-HPSv3	$-0.493$	7.9509	55.7763
	$(-0.478)$	$(+0.9484)$	$(+4.3388)$
GAL-Unipercept	$-0.171$	7.9841	58.6379

Table 4: Reward-signal ablation within GAL, evaluated by video and frame rewards on HunyuanVideo-1.5. Among the compared variants, GAL-VideoReward alone improves all three scores over Base on HunyuanVideo-1.5 and all three transfer models (Table 8 in Appendix H ). We therefore use it as the default variant. Metrics and parentheses follow Table 2 .

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

$m$	Pairs	Note
0.00	74,124	raw, drop ties only
0.05	52,084	operating point
0.10	33,781
0.15	20,421
0.20	11,672

Appendix

Table 5: DPO pair count as a function of the absolute reward margin threshold

m

on the GAL-VideoReward pair manifest. All reward variants use the same operating point,

m=0.05

, on their own reward-specific pair manifests (GAL-VideoReward: 52,084 pairs), each landing near a

\approx 5\times 10^{4}

-pair budget. A controlled pair-count sweep that holds data volume fixed across margins is listed as future work.

Split	# prompts	Source	Overlap with other splits
DPO train	$12{,}354$	Lexica corpus (cleaned, deduplicated)	$0$
VBench eval	$93$ / $72$ per dim	Official VBench per-dimension sets	$0$
Kling eval	$50$	Held-out Lexica (disjoint from train)	$0$

Appendix

Table 6: Prompt sources and disjointness audit. All overlap counts are computed after prompt canonicalization. The training and Kling pools are a disjoint train / held-out split of the Lexica corpus; the VBench pool is the official suite.

I2V model	Dynamic fraction $\uparrow$	Within-prompt var. (ddof=0) $\downarrow$	Within-prompt var. (ddof=1) $\downarrow$
LTX-Video	0.5556	0.10204	0.11132
CogVideoX-1.5	0.6481	0.07735	0.08439
HunyuanVideo-1.5	0.7963	0.03318	0.03620
WAN	0.8322	0.02865	0.03125

Appendix

Table 7: Anchor-seed sensitivity of the binary VBench dynamic-degree readout. For each of the 72 official VBench dynamic-degree prompts, we sample 12 seed-conditioned sibling anchors from the same T2I generator and render them with each frozen I2V model under a fixed downstream setting. VBench returns a binary label

d\in\{0,1\}

for each rendered clip. We report the overall dynamic fraction and the prompt-averaged within-prompt variance across the 12 seeds. Low variance means that changing the seed-conditioned anchor rarely changes the binary dynamic/static decision for the same prompt. WAN has the highest dynamic fraction and the lowest within-prompt variance, indicating a near-saturated and low-sensitivity dynamic-degree readout.

LTX-Video (transfer)
Variant	VideoReward Overall	HPSv3 (video frames)	UniPercept (video frames)
Base	$-0.328$	6.4788	50.0465
GAL-Image	$-0.763$	7.7409	55.7652
	$(-0.435)$	$(+1.2621)$	$(+5.7187)$
GAL-HPSv3	$-0.672$	7.7935	55.0136
	$(-0.344)$	$(+1.3147)$	$(+4.9671)$

Appendix

Table 8: Reward-model scores on the three transfer I2V models across GAL variants. VideoReward-Overall scores rendered clips; HPSv3 and UniPercept score their extracted frames. Parentheses give the absolute change from Base; bold marks the best value within each model.

Image-to-Video Generation

Image-to-video generation creates coherent moving clips from still images, guided by learned models and controls such as motion, camera, or text.

See all 95 papers

V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation
Jun 4, 2026Tao Liu, Leela Krishna, Gouti Pavan Kumar +2Video-Reference Video Generation Video Editing Benchmarks
Centific Global Solutions Inc.
Motif-Video 2B: Technical Report
Apr 14, 2026Junghwan Lim, Wai Ting Cheung, Minsu Ha +25T2V Generation Video Foundation Models
Motif Technologies
IsoVRBench: Video Reward Modeling Without Human Feedback
Oct 12, 2026Shuyue Stella Li, Jacqueline He, Jiahui Chen +5Reward Modeling Video Generation Evaluation
University of Washington · 2Meta Superintelligence Labs

Jun 4, 2026J/K move · Enter open · S save

V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation

Tao Liu, Leela Krishna, Gouti Pavan Kumar, Sreeja K+1

Centific Global Solutions Inc.

Video-Reference Video Generation Video Editing Benchmarks Video Generation Instruction-Based Video Editing Temporal Consistency in Video Generation Video Generation Evaluation

Open paper AskPDF arXiv

Video-to-video (V2V) generation is difficult to evaluate because outputs must both follow editing instructions and preserve frame-level correspondence with the source video, which existing T2V and I2V metrics do not capture. We introduce V2V-Bench, a 11-dimension benchmark organized into five categories: temporal alignment, structural fidelity, transformation quality, video quality, and semantic alignment. V2V-Bench pairs diverse source videos with challenging editing tasks and evaluates two commercial models, Grok Imagine and Gemini Veo3, and one open-source model, Open Sora 2. Results show complementary model strengths: Grok performs better on editing fidelity, while Veo3 achieves stronger visual quality. On six V2V-specific dimensions, V2V-Bench reaches a Spearman correlation of 0.905 with human judgments.

Abstract

Image-to-Video Generation

Explore similar work

V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation

Motif-Video 2B: Technical Report

IsoVRBench: Video Reward Modeling Without Human Feedback